@inproceedings{pietruszka-etal-2024-stable,
title = "{ST}able: Table Generation Framework for Encoder-Decoder Models",
author = "Pietruszka, Micha{\l} and
Turski, Micha{\l} and
Borchmann, {\L}ukasz and
Dwojak, Tomasz and
Nowakowska, Gabriela and
Szyndler, Karolina and
Jurkiewicz, Dawid and
Garncarek, {\L}ukasz",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.151",
pages = "2454--2472",
abstract = "The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Following this constatation, we propose a framework for text-to-table neural models applicable to problems such as extraction of line items, joint entity and relation extraction, or knowledge base population. The permutation-based decoder of our proposal is a generalized sequential method that comprehends information from all cells in the table. The training maximizes the expected log-likelihood for a table{'}s content across all random permutations of the factorization order. During the content inference, we exploit the model{'}s ability to generate cells in any order by searching over possible orderings to maximize the model{'}s confidence and avoid substantial error accumulation, which other sequential models are prone to. Experiments demonstrate a high practical value of the framework, which establishes state-of-the-art results on several challenging datasets, outperforming previous solutions by up to $15\\%$.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pietruszka-etal-2024-stable">
<titleInfo>
<title>STable: Table Generation Framework for Encoder-Decoder Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Pietruszka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Turski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Borchmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Dwojak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriela</namePart>
<namePart type="family">Nowakowska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Szyndler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Jurkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Garncarek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Following this constatation, we propose a framework for text-to-table neural models applicable to problems such as extraction of line items, joint entity and relation extraction, or knowledge base population. The permutation-based decoder of our proposal is a generalized sequential method that comprehends information from all cells in the table. The training maximizes the expected log-likelihood for a table’s content across all random permutations of the factorization order. During the content inference, we exploit the model’s ability to generate cells in any order by searching over possible orderings to maximize the model’s confidence and avoid substantial error accumulation, which other sequential models are prone to. Experiments demonstrate a high practical value of the framework, which establishes state-of-the-art results on several challenging datasets, outperforming previous solutions by up to 15\%.</abstract>
<identifier type="citekey">pietruszka-etal-2024-stable</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.151</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>2454</start>
<end>2472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STable: Table Generation Framework for Encoder-Decoder Models
%A Pietruszka, Michał
%A Turski, Michał
%A Borchmann, Łukasz
%A Dwojak, Tomasz
%A Nowakowska, Gabriela
%A Szyndler, Karolina
%A Jurkiewicz, Dawid
%A Garncarek, Łukasz
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F pietruszka-etal-2024-stable
%X The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Following this constatation, we propose a framework for text-to-table neural models applicable to problems such as extraction of line items, joint entity and relation extraction, or knowledge base population. The permutation-based decoder of our proposal is a generalized sequential method that comprehends information from all cells in the table. The training maximizes the expected log-likelihood for a table’s content across all random permutations of the factorization order. During the content inference, we exploit the model’s ability to generate cells in any order by searching over possible orderings to maximize the model’s confidence and avoid substantial error accumulation, which other sequential models are prone to. Experiments demonstrate a high practical value of the framework, which establishes state-of-the-art results on several challenging datasets, outperforming previous solutions by up to 15\%.
%U https://aclanthology.org/2024.eacl-long.151
%P 2454-2472
Markdown (Informal)
[STable: Table Generation Framework for Encoder-Decoder Models](https://aclanthology.org/2024.eacl-long.151) (Pietruszka et al., EACL 2024)
ACL
- Michał Pietruszka, Michał Turski, Łukasz Borchmann, Tomasz Dwojak, Gabriela Nowakowska, Karolina Szyndler, Dawid Jurkiewicz, and Łukasz Garncarek. 2024. STable: Table Generation Framework for Encoder-Decoder Models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2454–2472, St. Julian’s, Malta. Association for Computational Linguistics.